© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4541
    Prev
    Next
    INDEX
    Explanations

    code-like strings, including variables and file attributes, especially those related to data lifecycle management.

    oai_token-act-pair · gemini-2.0-flash

    code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.62
    ConstraintMaker
    -0.60
    MessageOf
    -0.60
    CardBody
    -0.58
    parsedMessage
    -0.58
    styleType
    -0.58
    kusen
    -0.56
    TextHelper
    -0.56
    GEBURTSDATUM
    -0.55
    localctx
    -0.54
    POSITIVE LOGITS
     recevez
    0.53
     Toad
    0.50
     chargés
    0.49
     déput
    0.48
     Tear
    0.48
     volete
    0.47
    fic
    0.47
     taş
    0.46
     représentants
    0.46
     gamla
    0.45
    Activations Density 0.618%

    No Known Activations